nthypes's comments

On: Show HN: Eve – Managed OpenClaw for work

[nthypes]

Vibeslop

On: Sam Altman's response to Molotov cocktail incident

[nthypes]

I have the same feelings

On: Show HN: Turbolite – a SQLite VFS serving sub-250ms cold JOIN queries from S3

[nthypes]

im also curious. GCS also charges per GET request

On: Show HN: I made an email app inspired by Arc browser

[nthypes]

Same here.

[zephyreon → nthypes]

And here.

[nssnsjsjsjs → zephyreon]

And not here

[endofreach → nssnsjsjsjs]

Same here.

On: I turned Markdown into a protocol for generative UI

[nthypes]

Why not MDX?

[FabianCarbonara → nthypes]

The goal isn't really a better markdown format — it's bringing code execution and generative UI together. The code fences run on the server: calling APIs, processing data, doing agentic work. And they can also mount reactive UIs with full data flow between client, server, and LLM.

MDX is a compile-time format for static content. This is a runtime protocol where the LLM writes code that executes as it streams, and the UIs it creates stay connected to the server.

On: Show HN: Axe – A 12MB binary that replaces your AI framework

[nthypes]

There is no "session" concept?

[jrswab → nthypes]

Not yet but is on the short list to implement. What would you need from a session for single purpose agents? I'm seeing it more as a way to track what's been done.

On: GPT-5.4

[nthypes]

$30/M Input and $180/M Output Tokens is nuts. Ridiculous expensive for not that great bump on intelligence when compared to other models.

[stri8ted → nthypes]

Price Input: $2.50 / 1M tokens Cached input: $0.25 / 1M tokens Output: $15.00 / 1M tokens

https://openai.com/api/pricing/

[nthypes → nthypes]

Gemini 3.1 Pro

$2/M Input Tokens $15/M Output Tokens

Claude Opus 4.6

$5/M Input Tokens $25/M Output Tokens

[nthypes → nthypes]

Just to clarify,the pricing above is for GPT-5.4 Pro. For standard here is the pricing:

$2.5/M Input Tokens $15/M Output Tokens

[energy123 → nthypes]

For Pro

[joe_mamba → nthypes]

Better tokens per dollar could be useless for comparison if the model can't solve your problem.

[rvz → nthypes]

You didn't realize they can increase / change prices for intelligence?

This should not be shocking.

[nickthegreek → rvz]

OP made no mention of not understanding cost relation to intelligence. In fact, they specifically call out the lack of value.

[moralestapia → nthypes]

Don't use it?

On: Show HN: I built a sub-500ms latency voice agent from scratch

[nthypes]

What about the costs?

On: The Future of AI Software Development

[nthypes]

IMHO, it doesn't, but I have changed the title to avoid any confusion.

On: The Future of AI Software Development

[nthypes]

IMHO, it doesn't, but I have changed the title to avoid any confusion.